mlsanityData to 7 Oct 2026

Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection

arXiv 2304.05096 ↗First posted 11 Apr 2023cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Two-stage object detectors generate object proposals and classify them to detect objects in images. These proposals often do not contain the objects perfectly but overlap with them in many possible ways, exhibiting great variability in the difficulty levels of the proposals. Training a robust classifier against this crop-related variability requires abundant training data, which is not available in few-shot settings. To mitigate this issue, we propose a novel variational autoencoder (VAE) based data generation model, which is capable of generating data with increased crop-related diversity. The main idea is to transform the latent space such latent codes with different norms represent different crop-related variations. This allows us to generate features with increased crop-related diversity in difficulty levels by simply varying the latent norm. In particular, each latent code is rescaled such that its norm linearly correlates with the IoU score of the input crop w.r.t. the ground-truth box. Here the IoU score is a proxy that represents the difficulty level of the crop. We train this VAE model on base classes conditioned on the semantic code of each class and then use the trained model to generate features for novel classes. In our experiments our generated features consistently improve state-of-the-art few-shot object detection methods on the PASCAL VOC and MS COCO datasets.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 40 of its 60 references that are in the map. First posted on arXiv 11 Apr 2023.

Builds on

40 of 60 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  7. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  8. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  9. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  10. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  11. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  12. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
28 more
  1. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  2. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  3. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  4. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  5. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  6. 2020Incremental Few-Shot Object Detectioncited by 102
  7. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  8. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  9. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  10. 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
  11. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  12. 2019Dont Even Look Once: Synthesizing Features for Zero-Shot Detectioncited by 58
  13. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
  14. 2018Learning Latent Subspaces in Variational Autoencoderscited by 51
  15. 2021Hallucination Improves Few-Shot Object Detectioncited by 50
  16. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  17. 2021Label, Verify, Correct: A Simple Few Shot Object Detection Methodcited by 43
  18. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  19. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  20. 2020Synthesizing the Unseen for Zero-shot Object Detectioncited by 32
  21. 2020Restoring Negative Information in Few-Shot Object Detectioncited by 28
  22. 2020Context-Transformer: Tackling Object Confusion for Few-Shot Detectioncited by 27
  23. 2020Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Reviewcited by 20
  24. 2022Robust Region Feature Synthesizer for Zero-Shot Object Detectioncited by 20
  25. 2016Co-localization with Category-Consistent Features and Geodesic Distance Propagationcited by 14
  26. 2021Few-Shot Learning for Road Object Detectioncited by 13
  27. 2019Weakly Labeling the Antarctic: The Penguin Colony Casecited by 12
  28. 2021Meta Guided Metric Learner for Overcoming Class Confusion in Few-Shot Road Object Detectioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 8; 2026: 2.

21 papers.

Sort:

By area:

  1. 2023Revisiting Few-Shot Object Detection with Vision-Language Modelscited by 32
  2. 2024All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seedscited by 31
  3. 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentationcited by 17
  4. 2024Assessing Sample Quality via the Latent Space of Generative Modelscited by 8
  5. 2025Multi-Perspective Data Augmentation for Few-shot Object Detectioncited by 6
  6. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  7. 2025Visual Textualization for Image Prompted Object Detectioncited by 6
  8. 2023The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentationcited by 5
  9. 2024BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairmentscited by 5
  10. 2024Shadow Removal Refinement via Material-Consistent Shadow Edgescited by 5
  11. 2025Few-shot Personalized Scanpath Predictioncited by 5
  12. 2024Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Densitycited by 3
9 more
  1. 2024Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentationcited by 2
  2. 2026DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detectioncited by 2
  3. 2023Decoupled DETR For Few-shot Object Detectioncited by 1
  4. 2024A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detectioncited by 1
  5. 2025CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentationcited by 1
  6. 2025Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detectioncited by 0
  7. 2025Few-Shot Object Detection via Spatial-Channel State Space Modelcited by 0
  8. 2025Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoningcited by 0
  9. 2026Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selectioncited by 0